Hybrid artificial intelligence-driven decision support system and method for real-time predictive industrial plant asset optimization

Abstract

A hybrid artificial intelligence-driven decision support system, for real-time predictive industrial plant asset optimization, uses real-time sensor data to generate a maintenance schedule for assets based on objectives for an industrial plant. The hybrid artificial intelligence-driven decision support system uses real-time sensor data to predict that the maintenance schedule, which is deployed, will not meet at least one of the objectives. The hybrid artificial intelligence-driven decision support system uses real-time sensor data to generate multiple optimized maintenance schedules for the assets, based on the objectives. A graphical user interface outputs the optimized maintenance schedules for the assets, with explanations how each optimized maintenance schedule would meet the objectives following deployment. The graphical user interface enables a selection and deployment of any one of the optimized maintenance schedules for the assets, thereby changing a scheduled time when an asset maintenance action is performed.

What is claimed is: 
     
         1 . A system for a hybrid artificial intelligence-driven decision support system for real-time predictive industrial plant asset optimization, the system comprising:
 one or more processors; and
 a non-transitory computer readable medium storing a plurality of instructions, which when executed, cause the one or more processors to: 
 generate, by a hybrid artificial intelligence-driven decision support system using real-time sensor data, a maintenance schedule for assets based on objectives for an industrial plant; 
 predict, by the hybrid artificial intelligence-driven decision support system using real-time sensor data, that the maintenance schedule, which is deployed, will not meet at least one of the objectives; 
 generate, by the hybrid artificial intelligence-driven decision support system using real-time sensor data, optimized maintenance schedules for the assets, based on the objectives; 
 output, via a graphical user interface, the optimized maintenance schedules for the assets, with explanations how each optimized maintenance schedule would meet the objectives following deployment; and 
 enable, by the graphical user interface, a selection and deployment of any one of the optimized maintenance schedules for the assets, thereby changing a scheduled time when an asset maintenance action is performed. 
   
     
     
         2 . The system of  claim 1 , wherein the hybrid artificial intelligence-driven decision support system comprises at least one of a predictive maintenance model, a physics-based process simulation model, or a probabilistic risk model for the assets of the industrial plant. 
     
     
         3 . The system of  claim 1 , wherein the objectives comprise a combination of a performance, a cost, a sustainability, or an equipment risk for an industrial plant. 
     
     
         4 . The system of  claim 1 , wherein the output, via the graphical user interface, further comprises comparisons of each optimized maintenance schedule to the deployed maintenance schedule. 
     
     
         5 . The system of  claim 4 , wherein the comparisons of each optimized maintenance schedule to the deployed maintenance schedule are based on depicting data values corresponding to at least three objectives for each maintenance schedule on a graph comprising at least three dimensions corresponding to the at least three objectives. 
     
     
         6 . The system of  claim 1 , wherein the plurality of instructions further causes the processor to assign, by the hybrid artificial intelligence-driven decision support system, at least one weight that corresponds to at least one of the objectives, in response to a selection to deploy an optimized maintenance schedule other than an optimized maintenance schedule that is ranked as more optimal than the other optimized maintenance schedules, thereby changing subsequent rankings of at least some of the optimized maintenance schedules. 
     
     
         7 . The system of  claim 1 , wherein the plurality of instructions further causes the processor to respond to deployment of the optimized maintenance schedule by the hybrid artificial intelligence-driven decision support system occasionally predicting whether the deployed optimized maintenance schedule will meet the objectives. 
     
     
         8 . A computer-implemented method for a hybrid artificial intelligence-driven decision support system for real-time predictive industrial plant asset optimization, the computer-implemented method comprising:
 generating, by a hybrid artificial intelligence-driven decision support system using real-time sensor data, a maintenance schedule for assets based on objectives for an industrial plant;   predicting, by the hybrid artificial intelligence-driven decision support system using real-time sensor data, that the maintenance schedule, which is deployed, will not meet at least one of the objectives;   generating, by the hybrid artificial intelligence-driven decision support system using real-time sensor data, optimized maintenance schedules for the assets, based on the objectives;   outputting, via a graphical user interface, the optimized maintenance schedules for the assets, with explanations how each optimized maintenance schedule would meet the objectives following deployment; and   enabling, by the graphical user interface, a selection and deployment of any one of the optimized maintenance schedules for the assets, thereby changing a scheduled time when an asset maintenance action is performed.   
     
     
         9 . The computer-implemented method of  claim 8 , wherein the hybrid artificial intelligence-driven decision support system comprises at least one of a predictive maintenance model, a physics-based process simulation model, or a probabilistic risk model for the assets of the industrial plant. 
     
     
         10 . The computer-implemented method of  claim 8 , wherein the objectives comprise a combination of a performance, a cost, a sustainability, or an equipment risk for an industrial plant. 
     
     
         11 . The computer-implemented method of  claim 8 , wherein the output, via the graphical user interface, further comprises comparisons of each optimized maintenance schedule to the deployed maintenance schedule. 
     
     
         12 . The computer-implemented method of  claim 11 , wherein the comparisons of each optimized maintenance schedule to the deployed maintenance schedule are based on depicting data values corresponding to at least three objectives for each maintenance schedule on a graph comprising at least three dimensions corresponding to the at least three objectives. 
     
     
         13 . The computer-implemented method of  claim 8 , wherein the computer-implemented method further comprises assigning, by the hybrid artificial intelligence-driven decision support system, at least one weight that corresponds to at least one of the objectives, in response to a selection to deploy an optimized maintenance schedule other than an optimized maintenance schedule that is ranked as more optimal than the other optimized maintenance schedules, thereby changing subsequent rankings of at least some of the optimized maintenance schedules. 
     
     
         14 . The computer-implemented method of  claim 8 , wherein the computer-implemented method further comprises responding to deployment of the optimized maintenance schedule by the hybrid artificial intelligence-driven decision support system occasionally predicting whether the deployed optimized maintenance schedule will meet the objectives. 
     
     
         15 . A computer program product, comprising a non-transitory computer-readable medium having a computer-readable program code embodied therein to be executed by one or more processors, the program code including instructions to:
 generate, by a hybrid artificial intelligence-driven decision support system using real-time sensor data, a maintenance schedule for assets based on objectives for an industrial plant;   predict, by the hybrid artificial intelligence-driven decision support system using real-time sensor data, that the maintenance schedule, which is deployed, will not meet at least one of the objectives;   generate, by the hybrid artificial intelligence-driven decision support system using real-time sensor data, optimized maintenance schedules for the assets, based on the objectives;   output, via a graphical user interface, the optimized maintenance schedules for the assets, with explanations how each optimized maintenance schedule would meet the objectives following deployment; and   enable, by the graphical user interface, a selection and deployment of any one of the optimized maintenance schedules for the assets, thereby changing a scheduled time when an asset maintenance action is performed.   
     
     
         16 . The computer program product of  claim 15 , wherein the hybrid artificial intelligence-driven decision support system comprises at least one of a predictive maintenance model, a physics-based process simulation model, or a probabilistic risk model for the assets of the industrial plant. 
     
     
         17 . The computer program product of  claim 15 , wherein the objectives comprise a combination of a performance, a cost, a sustainability, or an equipment risk for an industrial plant. 
     
     
         18 . The computer program product of  claim 15 , wherein the output, via the graphical user interface, further comprises comparisons of each optimized maintenance schedule to the deployed maintenance schedule based on depicting data values corresponding to at least three objectives for each maintenance schedule on a graph comprising at least three dimensions corresponding to the at least three objectives. 
     
     
         19 . The computer program product of  claim 15 , wherein the program code includes further instructions to assign, by the hybrid artificial intelligence-driven decision support system, at least one weight that corresponds to at least one of the objectives, in response to a selection to deploy an optimized maintenance schedule other than an optimized maintenance schedule that is ranked as more optimal than the other optimized maintenance schedules, thereby changing subsequent rankings of at least some of the optimized maintenance schedules. 
     
     
         20 . The computer program product of  claim 15 , wherein the program code includes further instructions to respond to deployment of the optimized maintenance schedule by the hybrid artificial intelligence-driven decision support system occasionally predicting whether the deployed optimized maintenance schedule will meet the objectives.